当前期刊: arXiv - CS - Machine Learning Go to current issue    加入关注   
显示样式:        排序: 导出
我的关注
我的收藏
您暂时未登录!
登录
  • TensorFlow Audio Models in Essentia
    arXiv.cs.LG Pub Date : 2020-03-16
    Pablo Alonso-Jiménez; Dmitry Bogdanov; Jordi Pons; Xavier Serra

    Essentia is a reference open-source C++/Python library for audio and music analysis. In this work, we present a set of algorithms that employ TensorFlow in Essentia, allow predictions with pre-trained deep learning models, and are designed to offer flexibility of use, easy extensibility, and real-time inference. To show the potential of this new interface with TensorFlow, we provide a number of pre-trained

    更新日期:2020-03-18
  • Neighborhood-based Pooling for Population-level Label Distribution Learning
    arXiv.cs.LG Pub Date : 2020-03-16
    Tharindu Cyril Weerasooriya; Tong Liu; Christopher M. Homan

    Supervised machine learning often requires human-annotated data. While annotator disagreement is typically interpreted as evidence of noise, population-level label distribution learning (PLDL) treats the collection of annotations for each data item as a sample of the opinions of a population of human annotators, among whom disagreement may be proper and expected, even with no noise present. From this

    更新日期:2020-03-18
  • ActiLabel: A Combinatorial Transfer Learning Framework for Activity Recognition
    arXiv.cs.LG Pub Date : 2020-03-16
    Parastoo Alinia; Iman Mirzadeh; Hassan Ghasemzadeh

    Sensor-based human activity recognition has become a critical component of many emerging applications ranging from behavioral medicine to gaming. However, an unprecedented increase in the diversity of sensor devices in the Internet-of-Things era has limited the adoption of activity recognition models for use across different domains. We propose ActiLabel a combinatorial framework that learns structural

    更新日期:2020-03-18
  • Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks
    arXiv.cs.LG Pub Date : 2020-03-16
    Sina Ghiassian; Banafsheh Rafiee; Yat Long Lo; Adam White

    Reinforcement learning systems require good representations to work well. For decades practical success in reinforcement learning was limited to small domains. Deep reinforcement learning systems, on the other hand, are scalable, not dependent on domain specific prior knowledge and have been successfully used to play Atari, in 3D navigation from pixels, and to control high degree of freedom robots

    更新日期:2020-03-18
  • Explaining Memorization and Generalization: A Large-Scale Study with Coherent Gradients
    arXiv.cs.LG Pub Date : 2020-03-16
    Piotr Zielinski; Shankar Krishnan; Satrajit Chatterjee

    Coherent Gradients is a recently proposed hypothesis to explain why over-parameterized neural networks trained with gradient descent generalize well even though they have sufficient capacity to memorize the training set. Inspired by random forests, Coherent Gradients proposes that (Stochastic) Gradient Descent (SGD) finds common patterns amongst examples (if such common patterns exist) since descent

    更新日期:2020-03-18
  • Parallel sequence tagging for concept recognition
    arXiv.cs.LG Pub Date : 2020-03-16
    Lenz FurrerUniversity of Zurich, SwitzerlandSwiss Institute of Bioinformatics, Switzerland; Joseph CorneliusUniversity of Zurich, Switzerland; Fabio RinaldiUniversity of Zurich, SwitzerlandDalle Molle Institute for Artificial Intelligence ResearchSwiss Institute of Bioinformatics, Switzerland

    Motivation: Named Entity Recognition (NER) and Normalisation (NEN) are core components of any text-mining system for biomedical texts. In a traditional concept-recognition pipeline, these tasks are combined in a serial way, which is inherently prone to error propagation from NER to NEN. We propose a parallel architecture, where both NER and NEN are modeled as a sequence-labeling task, operating directly

    更新日期:2020-03-18
  • Context-dependent self-exciting point processes: models, methods, and risk bounds in high dimensions
    arXiv.cs.LG Pub Date : 2020-03-16
    Lili Zheng; Garvesh Raskutti; Rebecca Willett; Benjamin Mark

    High-dimensional autoregressive point processes model how current events trigger or inhibit future events, such as activity by one member of a social network can affect the future activity of his or her neighbors. While past work has focused on estimating the underlying network structure based solely on the times at which events occur on each node of the network, this paper examines the more nuanced

    更新日期:2020-03-18
  • A Novel AI-enabled Framework to Diagnose Coronavirus COVID 19 using Smartphone Embedded Sensors: Design Study
    arXiv.cs.LG Pub Date : 2020-03-16
    Halgurd S. Maghdid; Kayhan Zrar Ghafoor; Ali Safaa Sadiq; Kevin Curran; Khaled Rabie

    Coronaviruses are a famous family of viruses that causes illness in human or animals. The new type of corona virus COVID-19 disease was firstly discovered in Wuhan-China. However, recently, the virus has been widely spread in most of the world countries and is reported as a pandemic. Further, nowadays, all the world countries are striving to control the coronavirus disease COVID-19. There are many

    更新日期:2020-03-18
  • Pretraining Image Encoders without Reconstruction via Feature Prediction Loss
    arXiv.cs.LG Pub Date : 2020-03-16
    Gustav Grund PihlgrenLuleå University of Technology; Fredrik SandinLuleå University of Technology; Marcus LiwickiLuleå University of Technology

    This work investigates three different loss functions for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced perceptual similarity loss, and a feature prediction loss proposed here; the latter turning out to be the most efficient choice. Former work shows that predictions based on embeddings generated by image autoencoders can be improved

    更新日期:2020-03-18
  • Real Time Detection of Small Objects
    arXiv.cs.LG Pub Date : 2020-03-17
    Al-Akhir Nayan; Joyeta Saha; Ahamad Nokib Mozumder; Khan Raqib Mahmud; Abul Kalam Al Azad

    The existing real time object detection algorithm is based on the deep neural network of convolution need to perform multilevel convolution and pooling operations on the entire image to extract a deep semantic characteristic of the image. The detection models perform better for large objects. However, these models do not detect small objects with low resolution and noise, because the features of existing

    更新日期:2020-03-18
  • Learnergy: Energy-based Machine Learners
    arXiv.cs.LG Pub Date : 2020-03-16
    Mateus Roder; Gustavo Henrique de Rosa; João Paulo Papa

    Throughout the last years, machine learning techniques have been broadly encouraged in the context of deep learning architectures. An interesting algorithm denoted as Restricted Boltzmann Machine relies on energy- and probabilistic-based nature to tackle with the most diverse applications, such as classification, reconstruction, and generation of images and signals. Nevertheless, one can see they are

    更新日期:2020-03-18
  • A Label Proportions Estimation technique for Adversarial Domain Adaptation in Text Classification
    arXiv.cs.LG Pub Date : 2020-03-16
    Zhuohao Chen

    Many text classification tasks are domain-dependent, and various domain adaptation approaches have been proposed to predict unlabeled data in a new domain. Domain-adversarial neural networks(DANN) and their variants have been actively used recently and have achieved state-of-the-art results for this problem. However, most of these approaches assume that the label proportions of the source and target

    更新日期:2020-03-18
  • A Numerical Transform of Random Forest Regressors corrects Systematically-Biased Predictions
    arXiv.cs.LG Pub Date : 2020-03-16
    Shipra Malhotra; John Karanicolas

    Over the past decade, random forest models have become widely used as a robust method for high-dimensional data regression tasks. In part, the popularity of these models arises from the fact that they require little hyperparameter tuning and are not very susceptible to overfitting. Random forest regression models are comprised of an ensemble of decision trees that independently predict the value of

    更新日期:2020-03-18
  • Object-Centric Image Generation from Layouts
    arXiv.cs.LG Pub Date : 2020-03-16
    Tristan Sylvain; Pengchuan Zhang; Yoshua Bengio; R Devon Hjelm; Shikhar Sharma

    Despite recent impressive results on single-object and single-domain image generation, the generation of complex scenes with multiple objects remains challenging. In this paper, we start with the idea that a model must be able to understand individual objects and relationships between objects in order to generate complex scenes well. Our layout-to-image-generation method, which we call Object-Centric

    更新日期:2020-03-18
  • Spectral Graph Attention Network
    arXiv.cs.LG Pub Date : 2020-03-16
    Heng Chang; Yu Rong; Tingyang Xu; Wenbing Huang; Somayeh Sojoudi; Junzhou Huang; Wenwu Zhu

    Variants of Graph Neural Networks (GNNs) for representation learning have been proposed recently and achieved fruitful results in various fields. Among them, graph attention networks (GATs) first employ a self-attention strategy to learn attention weights for each edge in the spatial domain. However, learning the attentions over edges only pays attention to the local information of graphs and greatly

    更新日期:2020-03-18
  • u-net CNN based fourier ptychography
    arXiv.cs.LG Pub Date : 2020-03-16
    Yican Chen; Zhi Luo; Xia Wu; Huidong Yang; Bo Huang

    Fourier ptychography is a recently explored imaging method for overcoming the diffraction limit of conventional cameras with applications in microscopy and yielding high-resolution images. In order to splice together low-resolution images taken under different illumination angles of coherent light source, an iterative phase retrieval algorithm is adopted. However, the reconstruction procedure is slow

    更新日期:2020-03-18
  • Task-Independent Spiking Central Pattern Generator: A Learning-Based Approach
    arXiv.cs.LG Pub Date : 2020-03-17
    Elie Aljalbout; Florian Walter; Florian Röhrbein; Alois Knoll

    Legged locomotion is a challenging task in the field of robotics but a rather simple one in nature. This motivates the use of biological methodologies as solutions to this problem. Central pattern generators are neural networks that are thought to be responsible for locomotion in humans and some animal species. As for robotics, many attempts were made to reproduce such systems and use them for a similar

    更新日期:2020-03-18
  • SlimConv: Reducing Channel Redundancy in Convolutional Neural Networks by Weights Flipping
    arXiv.cs.LG Pub Date : 2020-03-16
    Jiaxiong Qiu; Cai Chen; Shuaicheng Liu; Bing Zeng

    The channel redundancy in feature maps of convolutional neural networks (CNNs) results in the large consumption of memories and computational resources. In this work, we design a novel Slim Convolution (SlimConv) module to boost the performance of CNNs by reducing channel redundancies. Our SlimConv consists of three main steps: Reconstruct, Transform and Fuse, through which the features are splitted

    更新日期:2020-03-18
  • Catch the Ball: Accurate High-Speed Motions for Mobile Manipulators via Inverse Dynamics Learning
    arXiv.cs.LG Pub Date : 2020-03-17
    Ke Dong; Karime Pereida; Florian Shkurti; Angela P. Schoellig

    Mobile manipulators consist of a mobile platform equipped with one or more robot arms and are of interest for a wide array of challenging tasks because of their extended workspace and dexterity. Typically, mobile manipulators are deployed in slow-motion collaborative robot scenarios. In this paper, we consider scenarios where accurate high-speed motions are required. We introduce a framework for this

    更新日期:2020-03-18
  • AutoCogniSys: IoT Assisted Context-Aware Automatic Cognitive Health Assessment
    arXiv.cs.LG Pub Date : 2020-03-17
    Mohammad Arif Ul Alam; Nirmalya Roy; Sarah Holmes; Aryya Gangopadhyay; Elizabeth Galik

    Cognitive impairment has become epidemic in older adult population. The recent advent of tiny wearable and ambient devices, a.k.a Internet of Things (IoT) provides ample platforms for continuous functional and cognitive health assessment of older adults. In this paper, we design, implement and evaluate AutoCogniSys, a context-aware automated cognitive health assessment system, combining the sensing

    更新日期:2020-03-18
  • Towards High Performance, Portability, and Productivity: Lightweight Augmented Neural Networks for Performance Prediction
    arXiv.cs.LG Pub Date : 2020-03-17
    Ajitesh SrivastavaUniversity of Southern California; Naifeng ZhangUniversity of Southern California; Rajgopal KannanUS Army Research Lab-West; Viktor K. PrasannaUniversity of Southern California

    Writing high-performance code requires significant expertise of the programming language, compiler optimizations, and hardware knowledge. This often leads to poor productivity and portability and is inconvenient for a non-programmer domain-specialist such as a Physicist. More desirable is a high-level language where the domain-specialist simply specifies the workload in terms of high-level operations

    更新日期:2020-03-18
  • Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
    arXiv.cs.LG Pub Date : 2020-03-17
    Jongmin Yu; Yongsang Yoon; Moongu Jeon

    In skeleton-based action recognition, graph convolutional networks (GCNs), which model human body skeletons using graphical components such as nodes and connections, have achieved remarkable performance recently. However, current state-of-the-art methods for skeleton-based action recognition usually work on the assumption that the completely observed skeletons will be provided. This may be problematic

    更新日期:2020-03-18
  • Foundations of Explainable Knowledge-Enabled Systems
    arXiv.cs.LG Pub Date : 2020-03-17
    Shruthi Chari; Daniel M. Gruen; Oshani Seneviratne; Deborah L. McGuinness

    Explainability has been an important goal since the early days of Artificial Intelligence. Several approaches for producing explanations have been developed. However, many of these approaches were tightly coupled with the capabilities of the artificial intelligence systems at the time. With the proliferation of AI-enabled systems in sometimes critical settings, there is a need for them to be explainable

    更新日期:2020-03-18
  • Energy-Based Processes for Exchangeable Data
    arXiv.cs.LG Pub Date : 2020-03-17
    Mengjiao Yang; Bo Dai; Hanjun Dai; Dale Schuurmans

    Recently there has been growing interest in modeling sets with exchangeability such as point clouds. A shortcoming of current approaches is that they restrict the cardinality of the sets considered or can only express limited forms of distribution over unobserved data. To overcome these limitations, we introduce Energy-Based Processes (EBPs), which extend energy based models to exchangeable data while

    更新日期:2020-03-18
  • Directions for Explainable Knowledge-Enabled Systems
    arXiv.cs.LG Pub Date : 2020-03-17
    Shruthi Chari; Daniel M. Gruen; Oshani Seneviratne; Deborah L. McGuinness

    Interest in the field of Explainable Artificial Intelligence has been growing for decades and has accelerated recently. As Artificial Intelligence models have become more complex, and often more opaque, with the incorporation of complex machine learning techniques, explainability has become more critical. Recently, researchers have been investigating and tackling explainability with a user-centric

    更新日期:2020-03-18
  • Multi-action Offline Policy Learning with Bayesian Optimization
    arXiv.cs.LG Pub Date : 2020-03-17
    Fang Cai; Zhaonan Qu; Li Xia; Zhengyuan Zhou

    We study an offline multi-action policy learning algorithm based on doubly robust estimators from causal inference settings, using argmax linear policy function classes. For general policy classes, we establish the connection of the regret bound with a generalization of the VC dimension in higher dimensions and specialize this to prove optimal regret bounds for the argmax linear function class. We

    更新日期:2020-03-18
  • A Unified View of Label Shift Estimation
    arXiv.cs.LG Pub Date : 2020-03-17
    Saurabh Garg; Yifan Wu; Sivaraman Balakrishnan; Zachary C. Lipton

    Label shift describes the setting where although the label distribution might change between the source and target domains, the class-conditional probabilities (of data given a label) do not. There are two dominant approaches for estimating the label marginal. BBSE, a moment-matching approach based on confusion matrices, is provably consistent and provides interpretable error bounds. However, a maximum

    更新日期:2020-03-18
  • Neural Mesh Refiner for 6-DoF Pose Estimation
    arXiv.cs.LG Pub Date : 2020-03-17
    Di Wu; Yihao Chen; Xianbiao Qi; Yuyong Jian; Weixuan Chen; Rong Xiao

    How can we effectively utilise the 2D monocular image information for recovering the 6D pose (6-DoF) of the visual objects? Deep learning has shown to be effective for robust and real-time monocular pose estimation. Oftentimes, the network learns to regress the 6-DoF pose using a naive loss function. However, due to a lack of geometrical scene understanding from the directly regressed pose estimation

    更新日期:2020-03-18
  • Heat and Blur: An Effective and Fast Defense Against Adversarial Examples
    arXiv.cs.LG Pub Date : 2020-03-17
    Haya Brama; Tal Grinshpoun

    The growing incorporation of artificial neural networks (NNs) into many fields, and especially into life-critical systems, is restrained by their vulnerability to adversarial examples (AEs). Some existing defense methods can increase NNs' robustness, but they often require special architecture or training procedures and are irrelevant to already trained models. In this paper, we propose a simple defense

    更新日期:2020-03-18
  • Simultaneous Navigation and Radio Mapping for Cellular-Connected UAV with Deep Reinforcement Learning
    arXiv.cs.LG Pub Date : 2020-03-17
    Yong Zeng; Xiaoli Xu; Shi Jin; Rui Zhang

    Cellular-connected unmanned aerial vehicle (UAV) is a promising technology to unlock the full potential of UAVs in the future. However, how to achieve ubiquitous three-dimensional (3D) communication coverage for the UAVs in the sky is a new challenge. In this paper, we tackle this challenge by a new coverage-aware navigation approach, which exploits the UAV's controllable mobility to design its navigation/trajectory

    更新日期:2020-03-18
  • Efficient Bitwidth Search for Practical Mixed Precision Neural Network
    arXiv.cs.LG Pub Date : 2020-03-17
    Yuhang Li; Wei Wang; Haoli Bai; Ruihao Gong; Xin Dong; Fengwei Yu

    Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks. Recent efforts propose to quantize weights and activations from different layers with different precision to improve the overall performance. However, it is challenging to find the optimal bitwidth (i.e., precision) for weights and activations of each layer efficiently. Meanwhile

    更新日期:2020-03-18
  • Partial Multi-label Learning with Label and Feature Collaboration
    arXiv.cs.LG Pub Date : 2020-03-17
    Tingting Yu; Guoxian Yu; Jun Wang; Maozu Guo

    Partial multi-label learning (PML) models the scenario where each training instance is annotated with a set of candidate labels, and only some of the labels are relevant. The PML problem is practical in real-world scenarios, as it is difficult and even impossible to obtain precisely labeled samples. Several PML solutions have been proposed to combat with the prone misled by the irrelevant labels concealed

    更新日期:2020-03-18
  • Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild
    arXiv.cs.LG Pub Date : 2020-03-17
    Umar Iqbal; Pavlo Molchanov; Jan Kautz

    One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses. In this paper, we address this challenge by proposing a weakly-supervised approach that does not require 3D annotations and learns to estimate 3D poses from unlabeled multi-view data, which can be acquired easily in in-the-wild

    更新日期:2020-03-18
  • Nonlinear system identification with regularized Tensor Network B-splines
    arXiv.cs.LG Pub Date : 2020-03-17
    Ridvan Karagoz; Kim Batselier

    This article introduces the Tensor Network B-spline model for the regularized identification of nonlinear systems using a nonlinear autoregressive exogenous (NARX) approach. Tensor network theory is used to alleviate the curse of dimensionality of multivariate B-splines by representing the high-dimensional weight tensor as a low-rank approximation. An iterative algorithm based on the alternating linear

    更新日期:2020-03-18
  • Machine Learning the Phenomenology of COVID-19 From Early Infection Dynamics
    arXiv.cs.LG Pub Date : 2020-03-17
    Malik Magdon-Ismail

    We present a data-driven machine learning analysis of COVID-19 from its \emph{early} infection dynamics, with the goal of extracting actionable public health insights. We focus on the transmission dynamics in the USA starting from the first confirmed infection on January 21 2020. We find that COVID-19 has a strong infectious force if left unchecked, with a doubling time of under 3 days. However it

    更新日期:2020-03-18
  • Rectified Meta-Learning from Noisy Labels for Robust Image-based Plant Disease Diagnosis
    arXiv.cs.LG Pub Date : 2020-03-17
    Ruifeng Shi; Deming Zhai; Xianming Liu; Junjun Jiang; WenGao

    Plant diseases serve as one of main threats to food security and crop production. It is thus valuable to exploit recent advances of artificial intelligence to assist plant disease diagnosis. One popular approach is to transform this problem as a leaf image classification task, which can be then addressed by the powerful convolutional neural networks (CNNs). However, the performance of CNN-based classification

    更新日期:2020-03-18
  • A comprehensive study on the prediction reliability of graph neural networks for virtual screening
    arXiv.cs.LG Pub Date : 2020-03-17
    Soojung Yang; Kyung Hoon Lee; Seongok Ryu

    Prediction models based on deep neural networks are increasingly gaining attention for fast and accurate virtual screening systems. For decision makings in virtual screening, researchers find it useful to interpret an output of classification system as probability, since such interpretation allows them to filter out more desirable compounds. However, probabilistic interpretation cannot be correct for

    更新日期:2020-03-18
  • Fair inference on error-prone outcomes
    arXiv.cs.LG Pub Date : 2020-03-17
    Laura Boeschoten; Erik-Jan van Kesteren; Ayoub Bagheri; Daniel L. Oberski

    Fair inference in supervised learning is an important and active area of research, yielding a range of useful methods to assess and account for fairness criteria when predicting ground truth targets. As shown in recent work, however, when target labels are error-prone, potential prediction unfairness can arise from measurement error. In this paper, we show that, when an error-prone proxy target is

    更新日期:2020-03-18
  • Anomaly Detection in Video Data Based on Probabilistic Latent Space Models
    arXiv.cs.LG Pub Date : 2020-03-17
    Giulia Slavic; Damian Campo; Mohamad Baydoun; Pablo Marin; David Martin; Lucio Marcenaro; Carlo Regazzoni

    This paper proposes a method for detecting anomalies in video data. A Variational Autoencoder (VAE) is used for reducing the dimensionality of video frames, generating latent space information that is comparable to low-dimensional sensory data (e.g., positioning, steering angle), making feasible the development of a consistent multi-modal architecture for autonomous vehicles. An Adapted Markov Jump

    更新日期:2020-03-18
  • Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond
    arXiv.cs.LG Pub Date : 2020-03-17
    Wojciech Samek; Grégoire Montavon; Sebastian Lapuschkin; Christopher J. Anders; Klaus-Robert Müller

    With the broader and highly successful usage of machine learning in industry and the sciences, there has been a growing demand for explainable AI. Interpretability and explanation methods for gaining a better understanding about the problem solving abilities and strategies of nonlinear Machine Learning such as Deep Learning (DL), LSTMs, and kernel methods are therefore receiving increased attention

    更新日期:2020-03-18
  • Verification of Neural Networks: Enhancing Scalability through Pruning
    arXiv.cs.LG Pub Date : 2020-03-17
    Dario Guidotti; Francesco Leofante; Luca Pulina; Armando Tacchella

    Verification of deep neural networks has witnessed a recent surge of interest, fueled by success stories in diverse domains and by abreast concerns about safety and security in envisaged applications. Complexity and sheer size of such networks are challenging for automated formal verification techniques which, on the other hand, could ease the adoption of deep networks in safety- and security-critical

    更新日期:2020-03-18
  • Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
    arXiv.cs.LG Pub Date : 2020-03-17
    Hu Zhang; Linchao Zhu; Yi Zhu; Yi Yang

    Deep neural networks are known to be susceptible to adversarial noise, which are tiny and imperceptible perturbations. Most of previous work on adversarial attack mainly focus on image models, while the vulnerability of video models is less explored. In this paper, we aim to attack video models by utilizing intrinsic movement pattern and regional relative motion among video frames. We propose an effective

    更新日期:2020-03-18
  • Semi-Supervised Learning on Graphs with Feature-Augmented Graph Basis Functions
    arXiv.cs.LG Pub Date : 2020-03-17
    Wolfgang Erb

    For semi-supervised learning on graphs, we study how initial kernels in a supervised learning regime can be augmented with additional information from known priors or from unsupervised learning outputs. These augmented kernels are constructed in a simple update scheme based on the Schur-Hadamard product of the kernel with additional feature kernels. As generators of the positive definite kernels we

    更新日期:2020-03-18
  • Pool-Based Unsupervised Active Learning for Regression Using Iterative Representativeness-Diversity Maximization (iRDM)
    arXiv.cs.LG Pub Date : 2020-03-17
    Ziang Liu; Hanbin Luo; Weili Fang; Jiajing Liu; Dongrui Wu

    Active learning (AL) selects the most beneficial unlabeled samples to label, and hence a better machine learning model can be trained from the same number of labeled samples. Most existing active learning for regression (ALR) approaches are supervised, which means the sampling process must use some label information, or an existing regression model. This paper considers completely unsupervised ALR

    更新日期:2020-03-18
  • Inverse Design of Potential Singlet Fission Molecules using a Transfer Learning Based Approach
    arXiv.cs.LG Pub Date : 2020-03-17
    Akshay SubramanianDepartment of Metallurgical and Materials Engineering, Indian Institute of Technology Roorkee; Utkarsh SahaDepartment of Physics, Indian Institute of Technology Roorkee; Tejasvini SharmaDepartment of Physics, Indian Institute of Technology Roorkee; Naveen K. TailorDepartment of Physics, Indian Institute of Technology Roorkee; Soumitra SatapathiDepartment of Physics, Indian Institute

    Singlet fission has emerged as one of the most exciting phenomena known to improve the efficiencies of different types of solar cells and has found uses in diverse optoelectronic applications. The range of available singlet fission molecules is, however, limited as to undergo singlet fission, molecules have to satisfy certain energy conditions. Recent advances in material search using inverse design

    更新日期:2020-03-18
  • An Overview and Case Study of the Clinical AI Model Development Life Cycle for Healthcare Systems
    arXiv.cs.LG Pub Date : 2020-03-02
    Charles Lu; Julia Strout; Romane Gauriau; Brad Wright; Fabiola Bezerra De Carvalho Marcruz; Varun Buch; Katherine Andriole

    Healthcare is one of the most promising areas for machine learning models to make a positive impact. However, successful adoption of AI-based systems in healthcare depends on engaging and educating stakeholders from diverse backgrounds about the development process of AI models. We present a broadly accessible overview of the development life cycle of clinical AI models that is general enough to be

    更新日期:2020-03-18
  • Designing Tools for Semi-Automated Detection of Machine Learning Biases: An Interview Study
    arXiv.cs.LG Pub Date : 2020-03-13
    Po-Ming Law; Sana Malik; Fan Du; Moumita Sinha

    Machine learning models often make predictions that bias against certain subgroups of input data. When undetected, machine learning biases can constitute significant financial and ethical implications. Semi-automated tools that involve humans in the loop could facilitate bias detection. Yet, little is known about the considerations involved in their design. In this paper, we report on an interview

    更新日期:2020-03-18
  • The Data Science Fire Next Time: Innovative strategies for mentoring in data science
    arXiv.cs.LG Pub Date : 2020-03-01
    Latifa Jackson; Heriberto Acosta Maestre

    As data mining research and applications continue to expand in to a variety of fields such as medicine, finance, security, etc., the need for talented and diverse individuals is clearly felt. This is particularly the case as Big Data initiatives have taken off in the federal, private and academic sectors, providing a wealth of opportunities, nationally and internationally. The Broadening Participation

    更新日期:2020-03-18
  • ASR Error Correction and Domain Adaptation Using Machine Translation
    arXiv.cs.LG Pub Date : 2020-03-13
    Anirudh Mani; Shruti Palaskar; Nimshi Venkat Meripo; Sandeep Konam; Florian Metze

    Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch is still an issue for many such parties that want to use this service as-is leading to not so optimal results for their task. We propose a simple technique to perform

    更新日期:2020-03-18
  • Data-driven surrogate modelling and benchmarking for process equipment
    arXiv.cs.LG Pub Date : 2020-03-13
    Gabriel F. N. Gonçalves; Assen Batchvarov; Yuyi Liu; Yuxin Liu; Lachlan Mason; Indranil Pan; Omar K. Matar

    A suite of computational fluid dynamics (CFD) simulations geared towards chemical process equipment modelling has been developed and validated with experimental results from the literature. Various regression based active learning strategies are explored with these CFD simulators in-the-loop under the constraints of a limited function evaluation budget. Specifically, five different sampling strategies

    更新日期:2020-03-18
  • Audio inpainting with generative adversarial network
    arXiv.cs.LG Pub Date : 2020-03-13
    P. P. Ebner; A. Eltelt

    We study the ability of Wasserstein Generative Adversarial Network (WGAN) to generate missing audio content which is, in context, (statistically similar) to the sound and the neighboring borders. We deal with the challenge of audio inpainting long range gaps (500 ms) using WGAN models. We improved the quality of the inpainting part using a new proposed WGAN architecture that uses a short-range and

    更新日期:2020-03-18
  • Hybrid Autoregressive Transducer (hat)
    arXiv.cs.LG Pub Date : 2020-03-12
    Ehsan Variani; David Rybach; Cyril Allauzen; Michael Riley

    This paper proposes and evaluates the hybrid autoregressive transducer (HAT) model, a time-synchronous encoderdecoder model that preserves the modularity of conventional automatic speech recognition systems. The HAT model provides a way to measure the quality of the internal language model that can be used to decide whether inference with an external language model is beneficial or not. This article

    更新日期:2020-03-18
  • Linear Regression without Correspondences via Concave Minimization
    arXiv.cs.LG Pub Date : 2020-03-17
    Liangzu Peng; Manolis C. Tsakiris

    Linear regression without correspondences concerns the recovery of a signal in the linear regression setting, where the correspondences between the observations and the linear functionals are unknown. The associated maximum likelihood function is NP-hard to compute when the signal has dimension larger than one. To optimize this objective function we reformulate it as a concave minimization problem

    更新日期:2020-03-18
  • Nonparametric Deconvolution Models
    arXiv.cs.LG Pub Date : 2020-03-17
    Allison J. B. Chaney; Archit Verma; Young-suk Lee; Barbara E. Engelhardt

    We describe nonparametric deconvolution models (NDMs), a family of Bayesian nonparametric models for collections of data in which each observation is the average over the features from heterogeneous particles. For example, these types of data are found in elections, where we observe precinct-level vote tallies (observations) of individual citizens' votes (particles) across each of the candidates or

    更新日期:2020-03-18
  • Tensor Graph Convolutional Networks for Multi-relational and Robust Learning
    arXiv.cs.LG Pub Date : 2020-03-15
    Vassilis N. Ioannidis; Antonio G. Marques; Georgios B. Giannakis

    The era of "data deluge" has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and communications. In this context of graph-aware methods, the present paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that

    更新日期:2020-03-18
  • Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World
    arXiv.cs.LG Pub Date : 2020-03-17
    Daniel J. Fremont; Edward Kim; Yash Vardhan Pant; Sanjit A. Seshia; Atul Acharya; Xantha Bruso; Paul Wells; Steve Lemke; Qiang Yu; Shalin Mehta

    We present a new approach to automated scenario-based testing of the safety of autonomous vehicles, especially those using advanced artificial intelligence-based components, spanning both simulation-based evaluation as well as testing in the real world. Our approach is based on formal methods, combining formal specification of scenarios and safety properties, algorithmic test case generation using

    更新日期:2020-03-18
  • Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
    arXiv.cs.LG Pub Date : 2020-03-17
    Eunju Cha; Gyutaek Oh; Jong Chul Ye

    Recently, deep learning approaches have been extensively investigated to reconstruct images from accelerated magnetic resonance image (MRI) acquisition. Although these approaches provide significant performance gain compared to compressed sensing MRI (CS-MRI), it is not clear how to choose a suitable network architecture to balance the trade-off between network complexity and performance. Recently

    更新日期:2020-03-18
  • A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
    arXiv.cs.LG Pub Date : 2020-03-10
    Zequn Sun; Qingheng Zhang; Wei Hu; Chengming Wang; Muhao Chen; Farahnaz Akrami; Chengkai Li

    Entity alignment seeks to find entities in different knowledge graphs (KGs) that refer to the same real-world object. Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a continuous embedding space and measures entity similarities based on the learned embeddings. In this paper, we conduct a comprehensive experimental study of this emerging

    更新日期:2020-03-18
  • Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders
    arXiv.cs.LG Pub Date : 2020-03-17
    Yaniv Yacoby; Weiwei Pan; Finale Doshi-Velez

    Variational Auto-encoders (VAEs) are deep generative latent variable models consisting of two components: a generative model that captures a data distribution p(x) by transforming a distribution p(z) over latent space, and an inference model that infers likely latent codes for each data point (Kingma and Welling, 2013). Recent work shows that traditional training methods tend to yield solutions that

    更新日期:2020-03-18
  • Multi-modal Dense Video Captioning
    arXiv.cs.LG Pub Date : 2020-03-17
    Vladimir Iashin; Esa Rahtu

    Dense video captioning is a task of localizing interesting events from an untrimmed video and producing textual description (captions) for each localized event. Most of the previous works in dense video captioning are solely based on visual information and completely ignore the audio track. However, audio, and speech, in particular, are vital cues for a human observer in understanding an environment

    更新日期:2020-03-18
Contents have been reproduced by permission of the publishers.
导出
全部期刊列表>>
全球疫情及响应:BMC Medicine专题征稿
欢迎探索2019年最具下载量的化学论文
新版X-MOL期刊搜索和高级搜索功能介绍
化学材料学全球高引用
ACS材料视界
南方科技大学
x-mol收录
南方科技大学
自然科研论文编辑服务
上海交通大学彭文杰
中国科学院长春应化所于聪-4-8
武汉工程大学
课题组网站
X-MOL
深圳大学二维材料实验室张晗
中山大学化学工程与技术学院
试剂库存
天合科研
down
wechat
bug